How to Set Up Mistral AI (La Plateforme): A Practical Guide

# Test your key (replace YOUR_API_KEY)
curl --location "https://api.mistral.ai/v1/models" \
     --header "Authorization: Bearer YOUR_API_KEY" \
     --header "Content-Type: application/json"

{
  "object": "list",
  "data": [
    {
      "id": "mistral-small-latest",
      "object": "model",
      "created": 1693499933,
      "owned_by": "mistralai"
    },
    ...
  ]
}

export MISTRAL_API_KEY="your_key_here"

pip install mistralai --upgrade  # v0.3.0

from mistralai.client import MistralClient
from mistralai.models.chat_completion import ChatMessage

client = MistralClient(api_key=os.environ["MISTRAL_API_KEY"])
response = client.chat(
    model="mistral-small-latest",
    messages=[ChatMessage(role="user", content="Explain LLMs in 1 sentence")],
)

print(response.choices[0].message.content)

Large language models are neural networks trained on vast text data to predict and generate human-like text.

for chunk in client.chat_stream(
    model="mistral-medium-latest",
    messages=[ChatMessage(role="user", content="Write Python code to sort a list")],
):
    print(chunk.choices[0].delta.content, end="", flush=True)

npm install @mistralai/sdk

import { Mistral } from "@mistralai/sdk";

const client = new Mistral({ apiKey: process.env.MISTRAL_API_KEY });
const response = await client.chat({
  model: "mistral-small-latest",
  messages: [{ role: "user", content: "What's the capital of France?" }],
});

console.log(response.choices[0].message.content);

The capital of France is Paris.

models = ["mistral-small-latest", "mistral-medium-latest", "mistral-large-latest"]
for model in models:
    response = client.chat(
        model=model,
        messages=[ChatMessage(role="user", content="Write a Python function to reverse a string")],
    )
    print(f"\n{model}:\n{response.choices[0].message.content}")

response = client.chat(
    model="mistral-large-latest",
    messages=[ChatMessage(role="user", content="What's the latest news on Mistral AI?")],
    tools=[{"type": "web_search", "query": "Mistral AI latest news"}],
)

tools = [
    {
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get the current weather in a location",
            "parameters": {
                "type": "object",
                "properties": {
                    "location": {"type": "string", "description": "City name"},
                    "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
                },
                "required": ["location"],
            },
        },
    }
]

response = client.chat(
    model="mistral-large-latest",
    messages=[ChatMessage(role="user", content="What's the weather in Paris?")],
    tools=tools,
)

{
  "tool_calls": [
    {
      "function": {
        "name": "get_weather",
        "arguments": "{\"location\": \"Paris\", \"unit\": \"celsius\"}"
      }
    }
  ]
}

{"prompt": "What is Mistral AI?", "completion": "Mistral AI is a cutting-edge AI lab based in France..."}
{"prompt": "Who founded Mistral AI?", "completion": "Mistral AI was founded by Arthur Mensch, Guillaume Lample, and Timothée Lacroix in 2023."}

curl -X POST "https://api.mistral.ai/v1/fine_tuning/jobs" \
     -H "Authorization: Bearer $MISTRAL_API_KEY" \
     -H "Content-Type: application/json" \
     -d '{
       "model": "mistral-medium-2",
       "training_file": "file-123abc",  # Upload via console first
       "hyperparameters": {
         "n_epochs": 3,
         "batch_size": 8
       }
     }'

response = client.chat(
    model="ft:mistral-medium-2:your-org:custom-model-id",
    messages=[ChatMessage(role="user", content="What is Mistral AI?")],
)

agent = client.agents.create(
    name="TravelPlanner",
    model="mistral-large-latest",
    instructions="You are a travel planning assistant. Use tools to book flights and hotels.",
    tools=[
        {
            "type": "function",
            "function": {
                "name": "book_flight",
                "description": "Book a flight between two cities",
                "parameters": {
                    "type": "object",
                    "properties": {
                        "origin": {"type": "string"},
                        "destination": {"type": "string"},
                        "date": {"type": "string", "format": "date"},
                    },
                },
            },
        }
    ],
)

response = client.agents.run(
    agent_id=agent.id,
    messages=[{"role": "user", "content": "Plan a trip to Tokyo from Paris for next month"}],
)

jobs = client.batch.create(
    model="mistral-small-latest",
    input_file_ids=["file-123abc"],  # JSONL file with prompts
    endpoint="/v1/chat/completions",
)

from functools import lru_cache

@lru_cache(maxsize=100)
def get_cached_response(prompt):
    return client.chat(
        model="mistral-small-latest",
        messages=[ChatMessage(role="user", content=prompt)],
    )